Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and arguments related to clauses and verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    placement or order of words

    np_acts-logits-general · gemini-2.0-flash

    positional relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.73
    ")){
    -0.66
    sizeCache
    -0.66
    printStackTrace
    -0.64
     Symp
    -0.63
    ')['
    -0.61
    styleType
    -0.61
    AndroidJUnit
    -0.59
    __':
    -0.59
    modelBuilder
    -0.58
    POSITIVE LOGITS
     preceding
    1.23
     preceded
    1.16
     precede
    1.06
     followed
    1.03
     precedes
    0.99
     précé
    0.90
     preced
    0.82
     before
    0.81
     after
    0.80
    preced
    0.77
    Act Density 0.840%

    No Known Activations